FounderBrain

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the 300-word/15,000-word limits, typical runtime 'under a minute, up to about two minutes when the service is starting up,' and the note that MCP Apps clients also render a visual report.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The output shape is front-loaded in the first sentence, then parameters are explained compactly. There is minor structural sloppiness (a line break mid-sentence before 'role:', and the last sentence packing latency plus UI behavior together), but almost every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter, zero-schema-coverage tool with no output schema, the description covers inputs, output fields, prerequisites, and latency thoroughly. The one meaningful omission is any statement of how it relates to check_transcript, which is a plausible prerequisite/alternative the agent must otherwise guess about.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does so well: it defines the transcript format ('one speaker turn per line "Name: words"'), clarifies that 'speaker' is one label as it appears in the text, explains 'name' (used when the label is generic, 'You' for the user, required for generic labels other than Me), and gives the semantic intent of 'role' ('answering' when pitching/answering questions, 'asking' when mostly asking).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource plus a defined scope: 'Compare one speaker in a meeting transcript with public founder and operator interviews and return the report as data,' and it enumerates the output fields (speaking type, style positions, similar people, habits, takeaways). It is unambiguous what the tool produces, but it never names or distinguishes itself from the sibling check_transcript, which an agent will likely need to disambiguate against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states real preconditions (at least 300 words from the speaker, at most 15,000 words total) and expected latency, which help an agent decide whether a call is viable. However, it gives no explicit when-to-use / when-not-to-use guidance relative to the sibling check_transcript, so the choice between them is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the useful scope constraint that no scoring/evaluation occurs, but it says nothing about return shape or behavior on empty/malformed input.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and output, followed by the input format. No filler, though the indented second line is a formatting artifact rather than a content improvement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation, and the single parameter's format is documented. The definition is complete enough for an agent to call it correctly, missing only explicit sibling routing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameter burden, and it does: it defines the expected input format as one speaker turn per line in 'Name: words' form. That is a real contract beyond the bare string type in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the speakers in a meeting transcript') plus the derived output ('how many words each said'). It implicitly distinguishes itself from analyse_transcript via 'without scoring anything', but never names the sibling, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'without scoring anything' suggests this is the lightweight inventory tool as opposed to the analyse_* sibling, but there is no explicit when-to-use/when-not statement and no alternatives are named. Usage is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely useful behavior beyond that: this tool does not itself upload but returns a curl command for the client to run, and without a speaker argument it silently degrades to listing speakers and word counts only. That fallback behavior is not inferable from any structured field.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs, front-loaded with what the tool returns before parameter notes. The stray indentation is cosmetic, and nearly every sentence carries information, though the audience sentence could be tighter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value detail is not required. For a read-only, 4-parameter tool the description covers purpose, the client-execution model, the speaker fallback, and all parameters — enough to call it correctly. Only the sibling-routing guidance is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries full burden and largely meets it: path is a full local path with supported extensions (.docx, .txt, .md, .vtt), speaker is the label to analyse, name is the person's name when the label is generic, and role is 'answering' or 'asking'. Minor gaps remain — 'name' is only loosely defined and role's exact semantics are thin — but it materially compensates for the empty schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: returns a curl command that uploads a local transcript file to FounderBrain for analysis. It also scopes the audience ('clients that run commands on the user's own computer'), which implicitly separates it from server-side siblings, but it never names analyse_transcript or check_transcript, so sibling differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a usage condition — only for clients like Claude Code and Codex that execute commands locally — which is more than nothing. However, it never says when to prefer this over analyse_transcript or check_transcript, so the agent must guess from the environment description alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.